© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98704
    Prev
    Next
    INDEX
    Explanations

    compound phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stern
    -0.81
     Bur
    -0.78
    าหลี
    -0.76
     kompakt
    -0.75
    plastic
    -0.75
     konkre
    -0.74
    학
    -0.74
    inan
    -0.72
    вов
    -0.71
    nadier
    -0.70
    POSITIVE LOGITS
     electives
    0.85
     FaceTime
    0.79
    orari
    0.79
    服用
    0.78
    釆
    0.77
    rangian
    0.75
    SARS
    0.73
     WATCH
    0.73
    神奈川
    0.72
    suites
    0.72
    Activations Density 0.018%

    No Known Activations